{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JX6QOOCGF6IXZCA5MDVAAR6GR3","short_pith_number":"pith:JX6QOOCG","schema_version":"1.0","canonical_sha256":"4dfd0738462f917c881d60ea0047c68ed745248401e323e40aef2dbd56995985","source":{"kind":"arxiv","id":"2412.12433","version":1},"attestation_state":"computed","paper":{"title":"Refining Dimensions for Improving Clustering-based Cross-lingual Topic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chia-Hsuan Chang, Chia-Ming Chang, San-Yih Hwang, Tien-Yuan Huang, Yi-Hang Tsai","submitted_at":"2024-12-17T00:50:23Z","abstract_excerpt":"Recent works in clustering-based topic models perform well in monolingual topic identification by introducing a pipeline to cluster the contextualized representations. However, the pipeline is suboptimal in identifying topics across languages due to the presence of language-dependent dimensions (LDDs) generated by multilingual language models. To address this issue, we introduce a novel, SVD-based dimension refinement component into the pipeline of the clustering-based topic model. This component effectively neutralizes the negative impact of LDDs, enabling the model to accurately identify top"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.12433","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T00:50:23Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"80c5246b5a0ff04199e54466e40befb5f214e7dcbdf6b34a143a9ca7c159ba07","abstract_canon_sha256":"a0aedf2f164385d49894baf1fff0a6ab132ba0d7338c14147b50c20af627116d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:14.775093Z","signature_b64":"zzQSCVJK5BD259Nt23dhIDra15mws4dI1nJgGNLpmC5iHJ6vBXM9IuxyaY563ING/NK3WuszDnnV0WEmcWOxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dfd0738462f917c881d60ea0047c68ed745248401e323e40aef2dbd56995985","last_reissued_at":"2026-07-05T09:50:14.774601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:14.774601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Refining Dimensions for Improving Clustering-based Cross-lingual Topic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chia-Hsuan Chang, Chia-Ming Chang, San-Yih Hwang, Tien-Yuan Huang, Yi-Hang Tsai","submitted_at":"2024-12-17T00:50:23Z","abstract_excerpt":"Recent works in clustering-based topic models perform well in monolingual topic identification by introducing a pipeline to cluster the contextualized representations. However, the pipeline is suboptimal in identifying topics across languages due to the presence of language-dependent dimensions (LDDs) generated by multilingual language models. To address this issue, we introduce a novel, SVD-based dimension refinement component into the pipeline of the clustering-based topic model. This component effectively neutralizes the negative impact of LDDs, enabling the model to accurately identify top"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12433","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.12433/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.12433","created_at":"2026-07-05T09:50:14.774661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12433v1","created_at":"2026-07-05T09:50:14.774661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12433","created_at":"2026-07-05T09:50:14.774661+00:00"},{"alias_kind":"pith_short_12","alias_value":"JX6QOOCGF6IX","created_at":"2026-07-05T09:50:14.774661+00:00"},{"alias_kind":"pith_short_16","alias_value":"JX6QOOCGF6IXZCA5","created_at":"2026-07-05T09:50:14.774661+00:00"},{"alias_kind":"pith_short_8","alias_value":"JX6QOOCG","created_at":"2026-07-05T09:50:14.774661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JX6QOOCGF6IXZCA5MDVAAR6GR3","json":"https://pith.science/pith/JX6QOOCGF6IXZCA5MDVAAR6GR3.json","graph_json":"https://pith.science/api/pith-number/JX6QOOCGF6IXZCA5MDVAAR6GR3/graph.json","events_json":"https://pith.science/api/pith-number/JX6QOOCGF6IXZCA5MDVAAR6GR3/events.json","paper":"https://pith.science/paper/JX6QOOCG"},"agent_actions":{"view_html":"https://pith.science/pith/JX6QOOCGF6IXZCA5MDVAAR6GR3","download_json":"https://pith.science/pith/JX6QOOCGF6IXZCA5MDVAAR6GR3.json","view_paper":"https://pith.science/paper/JX6QOOCG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12433&json=true","fetch_graph":"https://pith.science/api/pith-number/JX6QOOCGF6IXZCA5MDVAAR6GR3/graph.json","fetch_events":"https://pith.science/api/pith-number/JX6QOOCGF6IXZCA5MDVAAR6GR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JX6QOOCGF6IXZCA5MDVAAR6GR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JX6QOOCGF6IXZCA5MDVAAR6GR3/action/storage_attestation","attest_author":"https://pith.science/pith/JX6QOOCGF6IXZCA5MDVAAR6GR3/action/author_attestation","sign_citation":"https://pith.science/pith/JX6QOOCGF6IXZCA5MDVAAR6GR3/action/citation_signature","submit_replication":"https://pith.science/pith/JX6QOOCGF6IXZCA5MDVAAR6GR3/action/replication_record"}},"created_at":"2026-07-05T09:50:14.774661+00:00","updated_at":"2026-07-05T09:50:14.774661+00:00"}